Three commands reimplemented from positively-received community PRs:
1. /gsd:review (#925) — Cross-AI peer review
Invoke external AI CLIs (Gemini, Claude, Codex) to independently
review phase plans. Produces REVIEWS.md with per-reviewer feedback
and consensus summary. Feed back into planning via --reviews flag.
Multiple users praised the adversarial review concept.
2. /gsd:plant-seed (#456) — Forward-looking idea capture
Capture ideas with trigger conditions that auto-surface during
/gsd:new-milestone. Seeds preserve WHY, WHEN to surface, and
breadcrumbs to related code. Better than deferred items because
triggers are checked, not forgotten.
3. /gsd:pr-branch (#470) — Clean PR branches
Create a branch for pull requests by filtering out .planning/
commits. Classifies commits as code-only, planning-only, or mixed,
then cherry-picks only code changes. Reviewers see clean diffs.
All three are standalone command+workflow additions with no core code
changes. Help workflow updated. Test skill counts updated.
797/797 tests pass.
Consolidates repeated path.join(cwd, '.planning', ...) patterns into
calls to the shared planningPaths() helper from core.cjs.
Modules updated:
- state.cjs: 16 → planningPaths() (2 remain for non-standard paths)
- commands.cjs: 8 → planningPaths() (4 remain for todos dir)
- milestone.cjs: 5 → planningPaths() (3 remain for archive/milestones)
- roadmap.cjs: 4 → planningPaths()
Benefits:
- Single source of truth for .planning/ directory structure
- Easier to change planning dir location in the future
- Consistent path construction across the codebase
- No behavioral changes — pure refactor
797/797 tests pass.
When GSD installs codex_hooks = true under [features], any non-boolean
keys already in that section (e.g. model = "gpt-5.4") cause Codex's
TOML parser to fail with 'invalid type: string, expected a boolean'.
Root cause: TOML sections extend until the next [section] header. If
the user placed model/model_reasoning_effort under [features] (common
since Codex's own config format encourages this), GSD's installer
didn't detect or correct the structural issue.
Fix: After injecting codex_hooks, scan the [features] section for
non-boolean values and move them above [features] to the top level.
This preserves the user's keys while keeping [features] clean for
Codex's strict boolean parser.
Includes 2 regression tests:
- Detects non-boolean keys under [features] (model, model_reasoning_effort)
- Confirms boolean keys (codex_hooks, multi_agent) are not flagged
Closes#1202
gsd-check-update.js scanned ALL .js files in the hooks directory and
flagged any without a gsd-hook-version header as stale. This incorrectly
flagged user-created hooks (e.g. guard-edits-outside-project.js),
producing a persistent 'stale hooks' warning that /gsd:update couldn't
resolve.
Fix: filter hookFiles to f.startsWith('gsd-') && f.endsWith('.js')
since all GSD hooks follow the gsd-* naming convention.
Includes regression test validating the filter excludes user hooks.
Closes#1200
* fix: universal agent name replacement for non-Claude runtimes (#766)
Adds neutralizeAgentReferences() shared function that all non-Claude
runtime converters call to replace Claude-specific references:
- 'Claude' (standalone agent name) → 'the agent'
- 'CLAUDE.md' → runtime-specific file (AGENTS.md, GEMINI.md, COPILOT.md)
- Removes 'Do NOT load full AGENTS.md' (harmful for AGENTS.md runtimes)
Preserves: 'Claude Code' (product), 'Claude Opus/Sonnet/Haiku' (models),
'claude-' prefixes (packages, CSS classes).
Integrated into: OpenCode, Gemini, Copilot, Antigravity, and Codex
converters. Claude Code converter unchanged (references are correct).
Includes 7 new tests covering all replacement rules.
Closes#766
* fix: use copilot-instructions.md instead of COPILOT.md for Copilot runtime
Addresses review from Solvely-Colin: Copilot's actual instruction file
is copilot-instructions.md, not COPILOT.md. The neutralizer was mapping
CLAUDE.md -> COPILOT.md which would reference a non-existent file.
- install.js: pass 'copilot-instructions.md' to neutralizeAgentReferences
- runtime-converters.test.cjs: update test to validate correct filename
New lightweight command for tasks too small to justify planning overhead:
typo fixes, config changes, forgotten commits, simple additions.
- Runs inline in current context (no subagent spawn)
- No PLAN.md or SUMMARY.md generated
- Scope guard: redirects to /gsd:quick if task needs >3 file edits
- Atomic commit with conventional commit format
- Logs to STATE.md quick tasks table if present
Complements /gsd:quick (which spawns planner+executor) for cases where
the planning overhead exceeds the actual work.
Closes#609
Keep `/gsd-*` command examples slash-prefixed during Cursor conversion while still normalizing legacy `gsd:` syntax, and add regression coverage for Next Up markdown output.
Made-with: Cursor
Prevent Cursor from treating frontmatter quotes as part of skill/subagent identifiers by emitting plain name scalars, and add regression tests to lock the conversion behavior.
Made-with: Cursor
Add a cross_reference_todos step to discuss-phase that surfaces relevant
backlog items before scope-setting decisions are made.
Implementation:
- New 'todo match-phase <N>' CLI command (commands.cjs) that scores
pending todos against a phase's ROADMAP goal using three heuristics:
keyword overlap, area match, and file path overlap
- New cross_reference_todos step in discuss-phase.md between
load_prior_context and scout_codebase
- CONTEXT.md template gains 'Folded Todos' subsection in <decisions>
and 'Reviewed Todos (not folded)' subsection in <deferred>
Design:
- No AI call for matching — pure keyword/area/file heuristics for speed
- Silent skip when todo_count is 0 or no matches (no workflow slowdown)
- Auto mode folds all todos with score >= 0.4 automatically
- Scoring: keywords (up to 0.6), area match (0.3), file overlap (0.4)
Tests: 5 new tests covering empty state, keyword matching, unrelated
todo exclusion, area matching, and score sorting.
Closes#1111
OpenCode does not recognize 'model: inherit' as a valid model identifier —
it throws ProviderModelNotFoundError when spawning any GSD subagent.
Changes:
- Remove 'model: inherit' injection for OpenCode agents in install.js
- Strip 'model:' field entirely during OpenCode frontmatter conversion
(OpenCode uses its configured default model when no model is specified)
- Update tests to verify model: inherit is NOT added
This fixes all 15 GSD agent definitions and the gsd-set-profile command
for OpenCode users.
Fixes#1156
Adds a zero-friction command that detects the current project state and
automatically invokes the next logical workflow step:
- No phases → discuss first phase
- Phase has no context → discuss
- Phase has context but no plans → plan
- Phase has plans but incomplete → execute
- All plans complete → verify and complete phase
- All phases complete → complete milestone
- Paused → resume work
No arguments needed — reads STATE.md, ROADMAP.md, and phase directories
to determine progression. Designed for multi-project workflows.
Closes#927
Previously, calling `mark-complete` on already-completed requirements
reported them as `not_found`, since the regex only matched unchecked
`[ ]` checkboxes and `Pending` table cells.
Now detects `[x]` checkboxes and `Complete` table cells and returns
them in a new `already_complete` array instead of `not_found`.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
PR #1084 added profile-user command and gsd-user-profiler agent but
didn't bump the hardcoded count assertions in copilot-install tests.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add Antigravity runtime support
Add full installation support for the Antigravity AI agent, bringing
get-shit-done capabilities to the new runtime alongside Claude Code,
OpenCode, Gemini, Codex, and Copilot.
- New runtime installation capability in bin/install.js
- Commands natively copied to the unified skills directory
- New test integration suite: tests/antigravity-install.test.cjs
- Refactored copy utility to accommodate Antigravity syntax
- Documentation added into README.md
Co-authored-by: Antigravity <noreply@google.com>
* fix: add missing processAttribution call in copyCommandsAsAntigravitySkills
Antigravity SKILL.md files were written without commit attribution metadata,
inconsistent with the Copilot equivalent (copyCommandsAsCopilotSkills) which
calls processAttribution on each skill's content before writing it.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: update Copilot install test assertions for 3 new UI agents
* docs: update CHANGELOG for Antigravity runtime support
---------
Co-authored-by: Antigravity <noreply@google.com>
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Strip unsupported `skills:` key from gsd-ui-auditor, gsd-ui-checker, and
gsd-ui-researcher agent frontmatter. Update Copilot install test expectations
to 36 skills / 15 agents.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add composable --research flag to /gsd:quick that spawns a focused
gsd-phase-researcher before planning. Investigates implementation
approaches, library options, and pitfalls for the task.
Addresses the middle-ground gap between quick (no quality agents) and
full milestone workflows. All three flags are composable:
--discuss --research --full gives the complete quality pipeline.
Made-with: Cursor
Co-authored-by: ralberts3 <ralberts3@gatech.edu>
* perf: make `/gsd:set-profile`'s implementation more programmatic
* perf: run the set-profile script without Claude needing to invoke it
- inject the script's output as dynamic context into the set-profile skill, so that Claude doesn't
need to invoke it and can simply read + print the output to the user
- reference: https://code.claude.com/docs/en/skills#inject-dynamic-context
* feat: improve output message for case where model profile wasn't changed
* feat: specify haiku model for set-profile command since it's so simple
* fix: remove ' (default)' from previousProfile to avoid false negative for didChange
* chore: add docstring to MODEL_PROFILES with note about the analogous markdown reference table
* chore: delete set-profile workflow file that's no longer needed
convertClaudeToOpencodeFrontmatter() was designed for commands but is
also called for agents. For agents it incorrectly strips name: (needed
by OpenCode agents), keeps color:/skills:/tools: (should strip), and
doesn't add model: inherit / mode: subagent (required by OpenCode).
Add isAgent option to convertClaudeToOpencodeFrontmatter() so agent
installs get correct frontmatter: name preserved, Claude-only fields
stripped, model/mode injected. Command conversion unchanged (default).
Includes 14 test cases covering agent and command conversion paths.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Phase numbers reset per milestone (v1.0 Phase 1-26, v1.1 Phase 1-6,
v1.2 Phase 1-6). Functions that searched ROADMAP.md for phase headings
or checkboxes would match archived milestone entries inside <details>
blocks before reaching the current milestone's entries.
This caused:
- roadmap_complete: true for phases that aren't complete (checkbox
regex matched the archived [x] Phase N from a previous milestone)
- phase-complete marking the wrong checkbox (archived instead of current)
- phase-add computing wrong maxPhase from archived headings
- progress not showing phases defined in ROADMAP but not yet on disk
Two bugs caused workflow.research to silently reset to false:
1. new-milestone.md unconditionally overwrote workflow.research via
config-set after asking about research — coupling a per-milestone
decision to a persistent user preference. Now the research question
is per-invocation only; persistent config changes via /gsd:settings.
2. verify.cjs health repair (createConfig/resetConfig) used flat keys
(research, plan_checker, verifier) instead of the canonical nested
workflow object from config.cjs, also missing branch templates,
nyquist_validation, and brave_search fields.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Add a new `/gsd:stats` command that displays comprehensive project
statistics including phase progress, plan execution metrics, requirements
completion, git history, and timeline information.
- New command definition: commands/gsd/stats.md
- New workflow: get-shit-done/workflows/stats.md
- CLI handler: `gsd-tools stats [json|table]`
- Stats function in commands.cjs with JSON and table output formats
- 5 new tests covering empty project, phase/plan counting, requirements
counting, last activity, and table format rendering
Co-authored-by: ashanuoc <ashanuoc@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
- Scope phase section regex to prevent cross-phase boundary matching
- Handle 'In Progress' status in traceability table (not just 'Pending')
- Add requirements_updated field to phase complete result object
- Add 3 new tests: result field, In Progress status, cross-boundary safety
Co-authored-by: ashanuoc <ashanuoc@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: remove deprecated Codex config keys causing UI instability (closes#1037)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: update codex config tests to match simplified config structure
Tests asserted the old config structure ([features] section, multi_agent,
default_mode_request_user_input, [agents] table with max_threads/max_depth)
that was deliberately removed. Tests now verify the new behavior: config
block contains only the GSD marker and per-agent [agents.gsd-*] sections.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: remove dangling skills: from agent frontmatter and strip in Gemini converter (closes#1023, closes#953, closes#930)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: invert skills frontmatter test to assert absence (fixes CI)
The PR deliberately removed skills: from agent frontmatter (breaks
Gemini CLI), but the test still asserted its presence. Inverted the
assertion to ensure skills: stays removed.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: plan-phase Nyquist validation when research is disabled (#980)
plan-phase step 5.5 required Nyquist artifacts even when research was
disabled, creating an impossible state: no RESEARCH.md to extract
Validation Architecture from. Step 7.5 then told Claude to "disable
Nyquist in config" without specifying the exact key, causing Claude to
guess wrong keys that config-set silently accepted.
Three fixes:
- plan-phase step 5.5: skip when research_enabled is false
- plan-phase step 7.5: specify exact config-set command for disabling
- config-set: reject unknown keys with whitelist validation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* test: update config-set tests for key whitelist validation
Tests that used arbitrary keys (some_number, some_string, a.b.c) now
use valid config keys to test the same coercion and nesting behavior.
Adds new test asserting unknown keys are rejected with error.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Quick task IDs were sequential integers (001, 002...) computed by reading
the local .planning/quick/ directory max value. Two users running /gsd:quick
simultaneously would get the same number, causing directory collisions on git.
Replace with a collision-resistant format: YYMMDD-xxx where xxx is the
number of 2-second blocks elapsed since midnight, encoded as 3 lowercase
Base36 characters (000–xbz). Practical collision window is ~2 seconds per
user — effectively zero for any realistic team workflow.
- init.cjs: remove nextNum scan logic, generate quickId from wall clock
- quick.md: rename all next_num refs to quick_id, update directory patterns
- init.test.cjs: rewrite cmdInitQuick tests for new ID format
Co-authored-by: yanbing <yanbing@corp.netease.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
* fix: change nyquist_validation default to true and harden absent-key skip conditions
new-project.md never wrote the key, so agents reading config directly
treated absent as falsy. Changed all agent skip conditions from "is false"
to "explicitly set to false; absent = enabled". Default changed from false
to true in core.cjs, config.cjs, and templates/config.json.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix: enforce VALIDATION.md creation with verification gate and Check 8e
Step 5.5 was narrative markdown that Claude skipped under context pressure.
Now MANDATORY with Write tool requirement and file-existence verification.
Step 7.5 gates planner spawn on VALIDATION.md presence. Check 8e blocks
Dimension 8 if file missing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add W008/W009 health checks and addNyquistKey repair for Nyquist drift detection
W008 warns when workflow.nyquist_validation key is absent from config.json
(agents may skip validation). W009 warns when RESEARCH.md has Validation
Architecture section but no VALIDATION.md file exists. addNyquistKey repair
adds the missing key with default true value.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: add /gsd:validate-phase command and gsd-nyquist-auditor agent
Retroactively applies Nyquist validation to already-executed phases.
Works mid-milestone and post-milestone. Detects existing test coverage,
maps gaps to phase requirements, writes missing tests, debugs failing
ones, and produces {phase}-VALIDATION.md from existing artifacts.
Handles three states: VALIDATION.md exists (audit + update), no
VALIDATION.md (reconstruct from PLAN.md + SUMMARY.md), phase not yet
executed (exit cleanly with guidance).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* feat: audit-milestone reports Nyquist compliance gaps across phases
Adds Nyquist coverage table to audit-milestone output when
workflow.nyquist_validation is true. Identifies phases missing
VALIDATION.md or with nyquist_compliant: false/partial.
Routes to /gsd:validate-phase for resolution. Updates USER-GUIDE
with retroactive validation documentation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* refactor: compress Nyquist prompts to match GSD meta-prompt density conventions
Auditor agent: deleted philosophy section (35 lines), compressed execution
flow 60%, removed redundant constraints. Workflow: cut purpose bloat,
collapsed state narrative, compressed auditor spawn template. Command:
removed redundant process section. Plan-phase Steps 5.5/7.5: replaced
hedging language with directives. Audit-milestone Step 5.5: collapsed
sub-steps into inline instructions. Net: -376 lines.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Two hardening changes to cmdMilestoneComplete:
1. Replace 27 lines of inline isDirInMilestone logic (roadmap parsing,
normalization, and matching) with a single call to the shared
getMilestonePhaseFilter(cwd) from core.cjs. The inline copy was
identical to the core version — deduplicating prevents future drift.
2. Handle empty MILESTONES.md files. Previously, an existing but empty
file would fall into the headerMatch branch and produce malformed
output. Now an empty file is treated the same as a missing one,
writing the standard "# Milestones" header before the entry.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
